Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 212 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0003

Data Index: 190982 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1116378 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0308. Min Act: -0.0003

Data Index: 270441 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0301. Min Act: -0.0003

Data Index: 876365 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1168011 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1184932 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0274. Min Act: -0.0003

Data Index: 760264 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0274. Min Act: -0.0003

Data Index: 42601 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1507288 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0277. Min Act: -0.0003

Data Index: 227170 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1326201 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0273. Min Act: -0.0003

Data Index: 967918 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0266. Min Act: -0.0003

Data Index: 674991 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0260. Min Act: -0.0003

Data Index: 290917 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0257. Min Act: -0.0002

Data Index: 286292 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0258. Min Act: -0.0003

Data Index: 269731 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0253. Min Act: -0.0003

Data Index: 592230 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0252. Min Act: -0.0003

Data Index: 440133 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1042611 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0254. Min Act: -0.0003

Data Index: 478018 (C4 (Web Text))

Max Activating Token Index: 748